Academic Risk Analysis of University Students Using Random Forest and SHAP
DOI:
https://doi.org/10.47709/cnahpc.v8i4.9625Dimension:
Keywords:
academic risk; explainable artificial intelligence; Random Forest; SHAP; SMOTE; student analyticsAbstract
Background: Academic risk classification can help universities identify students who require closer academic monitoring, but imbalanced classes and limited model transparency can reduce practical usefulness. Objective: This study develops a Random Forest classifier for academic-risk categories and explains model decisions using SHAP. Methods: The study used academic data from 484 Computer Science students at Universitas Islam Negeri Sumatera Utara for the 2025/2026 odd-to-even academic period. The target was formed using rule-based indicators, while the final predictors were Jumlah_MK (number of courses), Praktikum (practicum courses), and MK_Berat (heavy courses). Data were split stratified into 387 training and 97 testing observations. SMOTE was applied only to training folds during stratified five-fold cross-validation and again to the complete training set for the final model. Results: Cross-validation produced mean Accuracy 91.72%, Precision 46.05%, Recall 81.33%, F1-Score 58.21%, and ROC-AUC 90.46%. On the original testing set, the model achieved Accuracy 97.94%, Precision 85.71%, Recall 85.71%, F1-Score 85.71%, and ROC-AUC 98.65%, with TN=89, FP=1, FN=1, and TP=6. Feature Importance and Mean Absolute SHAP both ranked Jumlah_MK as the most influential predictor. Conclusion: Random Forest with training-only SMOTE provided strong testing performance and improved minority-class detection, while SHAP added an interpretable layer. The results should be interpreted cautiously because the high-risk class was small and the study used a single academic period.
Downloads
References
Ananda, L. F., Dewi, M. R., & Habibi, M. R. (2024). Explainable machine learning dalam analisis risiko akademis mahasiswa Fakultas Vokasi Institut Teknologi Sepuluh Nopember. IJAI (Indonesian Journal of Applied Informatics), 9(1), 113–123. https://doi.org/10.20961/ijai.v9i1.94691
Antonini, A. S., Tanzola, J., Asiain, L., Ferracutti, G. R., Castro, S. M., Bjerg, E. A., & Ganuza, M. L. (2024). Machine learning model interpretability using SHAP values: Application to igneous rock classification task. Applied Computing and Geosciences, 23, 100178. https://doi.org/10.1016/j.acags.2024.100178
Er, E. (2023). An explainable machine learning approach to predicting and understanding dropouts in MOOCs. Kastamonu E?itim Dergisi, 31(1), 143–154. https://doi.org/10.24106/kefdergi.1246458
Firman, M. A., Djamalilleil, S. A. F., Zega, W., Efrizoni, L., & Rahmaddeni. (2025). Model klasifikasi IPK mahasiswa menggunakan algoritma Decision Tree dan Random Forest berbasis feature engineering. TechnoCom, 24(2). https://doi.org/10.62411/tc.v24i2.12384
Fitriani, S., Budiman, E., Fadli, M., Surono, M., & Sulistiani, H. (2025). Optimalisasi metode Random Forest menggunakan particle swarm optimization dalam prediksi prestasi mahasiswa. Prosiding Seminar Nasional Teknologi Komputer dan Sains (SAINTEKS), 3(1), 406–415.
Gori, T., & Hestiningtyas, A. (2024). Optimasi pemilihan fitur untuk prediksi penyakit jantung menggunakan algoritma genetika dan Random Forest. Jurnal Ilmu Komputer Indonesia, 13(5). https://doi.org/10.33022/ijcs.v13i5.4214
Hapsari, L. N., Fannani, I., Rahmawati, Y., & Muhariya, A. (2026). Explainable machine learning untuk prediksi risiko penyakit jantung menggunakan Random Forest dan analisis SHAP. REMIK: Riset dan E-Jurnal Manajemen Informatika Komputer, 10(1), 190–199. https://doi.org/10.33395/remik.v10i1.15766
Helmud, E., Fitriyani, F., & Romadiana, P. (2024). Classification comparison performance of supervised machine learning Random Forest and Decision Tree algorithms using Confusion Matrix. Jurnal Sisfokom (Sistem Informasi Dan Komputer), 13(1), 92–97. https://doi.org/10.32736/sisfokom.v13i1.1985
Hidayatulloh, W., Mahardika, F., & Junaedi, D. I. (2026). Explainable Artificial Intelligence-based model for student academic performance prediction. Journal of Information System Exploration and Research, 4(1), 31–40. https://doi.org/10.52465/joiser.v4i1.624
Istiwana, A. P., Sani, R. R., & Pramudi, Y. T. C. (2026). Pendekatan explainable machine learning untuk analisis faktor drop out mahasiswa menggunakan XGBoost. Rabit: Jurnal Teknologi Dan Sistem Informasi Univrab, 11(1), 1074–1083. https://doi.org/10.36341/rabit.v11i1.7218
Junaidi, S., Anggela, R. V., & Kariman, D. (2024). Klasifikasi metode data mining untuk prediksi kelulusan tepat waktu mahasiswa dengan algoritma Naïve Bayes, Random Forest, Support Vector Machine (SVM) dan Artificial Neural Network (ANN). JACOST: Journal of Applied Computer Science and Technology, 5(1). https://doi.org/10.52158/jacost.v5i1.489
Kocsis, Á., & Molnár, G. (2025). Factors influencing academic achievement and dropout rates in higher education. Oxford Review of Education, 51(3), 414–432. https://doi.org/10.1080/03054985.2024.2316616
Li, Z. (2022). Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost. Computers, Environment and Urban Systems, 96, 101845. https://doi.org/10.1016/j.compenvurbsys.2022.101845
Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765–4774). Curran Associates, Inc.
Morán, P. L., Torres, J. R., & Cruz, A. M. (2025). Identifying key factors of student dropout through Random Forest: A data-driven approach. Applied Sciences, 15(4), 1256. https://doi.org/10.3390/app15041256
Nurmalitasari, Long, Z. A., & Noor, M. F. M. (2023). Factors influencing dropout students in higher education. Education Research International, 2023, Article 7704142. https://doi.org/10.1155/2023/7704142
Pajung, K. K. M., Komansilan, T., Kawilarang, G. J. C., Thomas, M. J., Nonga, R. G. P., Sumeke, E. A., Kereh, G., & Kiwo, M. (2026). Klasifikasi perilaku belajar mahasiswa menggunakan Random Forest Classifier berbasis Learning Behavior Questionnaire. EduTIK: Jurnal Pendidikan Teknologi Informasi dan Komunikasi, 6(2).
Pratiwi, A. N., & Utami, E. (2025). Predicting students’ academic performance in mathematics based on Big Five personality traits using Random Forest with Synthetic Minority Over-sampling Technique. Sistemasi: Jurnal Sistem Informasi, 14(2). https://doi.org/10.32520/stmsi.v14i2.5102
Putra, A. P., Sari, N. P., & Wijaya, R. (2025). Student dropout prediction using Random Forest and XGBoost method. Journal of Educational Data Mining and Analytics, 7(2), 145–158.
Saputra, P. S. (2026). Analisis prediktif dropout mahasiswa berdasarkan kinerja akademik semester awal menggunakan machine learning. Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI), 7(1), 164–171. https://doi.org/10.30998/ed38e865
Sulehu, M., Wisda, W., Wanita, F., & Markani. (2025). Optimasi prediksi kelulusan mahasiswa menggunakan Random Forest untuk meningkatkan tingkat retensi. Jurnal Minfo Polgan, 13(2), 2364–2374. https://doi.org/10.33395/jmp.v13i2.14472
Tamsir, I. S., Putrada, A. G., & Wicaksono, R. L. (2026). SHAP dalam explainable AI untuk deteksi depresi mahasiswa menggunakan AdaBoost. e-Proceeding of Engineering, 13(3), 29661–29727.
Zawiyah, S., Qodriyah, L., & Tamam, M. B. (2024). Klasifikasi prestasi akademik mahasiswa menggunakan metode Random Forest. Jobit: Journal of Digital Business and Information Technology, 1(2). https://doi.org/10.23971/jobit.v1i2.317
Zulfa, E., Amir, H., Ginting, R., & Sudarno. (2024). Analisis korelasi kesehatan mental dan indeks prestasi mahasiswa Jurusan Administrasi Niaga Politeknik Negeri Jakarta dengan kombinasi metode XGBoost dan SHAP. JAProf: Jurnal Administrasi Profesional, 5(1), 26–37. https://doi.org/10.32722/jap.v5i1.6923
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Nouval Khairi, Reza Ade Putra
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
